AI agents call get_new_messages to retrieve information from MaaMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates a read-only operation that retrieves new messages without side effects. However, confidence is moderate (0.6) because the description is empty and cannot provide definitive evidence of the tool's actual capabilities. In the context of an Android/Windows automation server, this likely queries message data from the device, which is a Read operation.
From the tool's definition Tool name 'get_new_messages' suggests retrieval/querying of message data with no modification. No description provided to confirm exact behavior.
Attacks that exploit this kind of access
get_new_messages. It is categorised as a Read tool in the MaaMCP MCP Server, which means it retrieves data without modifying state.
Register the Maa MCP server in PolicyLayer and add a rule for get_new_messages: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MaaMCP. Nothing to install.
get_new_messages is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_new_messages rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_new_messages. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_new_messages is provided by the Maa MCP server (maa-ai/maamcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →